Jan, 2020: SOKO JKU: Philipp Schwarz was awarded the Adolf Adam Computer Science Prize for his program, which can read usable profiles even from badly preserved fingerprints. More info: bit.ly/36TlCoz
Nov, 2019: Best Paper Award at ISMIR2019 goes to a paper by our PhD student Stefan Lattner (Sony CSL, Paris) and Andreas Arzt (PostDoc at our institute, now with Apple, Hamburg). Congratulations!
Nov, 2019: Invited talk by Hamid Eghbal-zadeh at the Intelligent Autonomous Systems Group of the Computer Science Department of the Technische Universitaet Darmstadt: Representation Learning under Incomplete and Imprecise Information Conditions.
Okt, 2019: Judges' award at the DCASE2019: The CP Team, Paul Primus and David Eitelsebner, won the Judges' award at the DCASE2019 challenge Task1 for "Acoustic Scene Classification with Mismatched Recording Devices".
Okt, 2019: Best student paper award at the DCASE2019: The Team of CP, Paul Primus, Hamid Eghbal-zadeh, David Eitelsebner, Khaled Koutini, Andreas Arzt, Gerhard Widmer, won Best student paper award at the DCASE2019 workshop for the paper "Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification".
Okt, 2019: Markus Schedl gives an interview in the dorf-tv series "Hörstadtgespräche", on the topics of Social Media Mining, Selection of Music, Listener Profiles, and Music Recommendation.
Listening only to music that Spotify suggests - is that our future? Will we then notice that we only listen to what we already know because
we like it? These and other questions are discussed in the interview with Prof. Markus Schedl, who researches music listener profiles and music recommendation systems. The video is in German. Video
Okt, 2019: Explainable Models and Their Application in Music Emotion Recognition: ARI guest talk by Verena Haunschmid and Shreyan Chowdhury at the Acoustics Research Institute of the Austrian Academy of Sciences, Vienna. View more
Okt, 2019: Gerhard Widmer to give a Keynote Presentation at the Augmenting Performance Conference. Much of current research in Artificial Intelligence and Music, and particularly in the field of Music Information Retrieval (MIR), focuses on algorithms that interpret musical signals and recognise musically relevant objects and patterns at various levels – from notes to beats and rhythm, to melodic and harmonic patterns and higher-level structure -, with the goal of supporting novel applications in the digital music world. This presentation will give the audience a glimpse of what computational music perception systems can currently do with music, and what this is good for. However, we will also find that while some of these capabilities are quite impressive, they are still far from showing (or requiring) a deeper „understanding” of music. An ongoing project will be presented that aims to take AI & music research a step further, going beyond surface features and focusing on the *expressive* aspects, and how these are communicated in music. We will look at recent work on computational models of expressive music performance and some examples of the state of the art, and will discuss possible applications of this research. In the process, the audience will be subjected to a little experiment which may, or may not, yield a surprising result. View more
Sep, 2019: CP’s researcher Christine Bauer on the Austrian public radio Ö1 on music and technology, and their impact on the music industry. Among other experts in the field, the Radiokolleg will feature CP’s researcher Christine Bauer in part 2 and 4 of the program (1st and 3rd October 2019, respectively).
Sep, 2019: CP-JKU achieves first place in `emotion and theme recognition in music challenge, MediaEval 19.
MediaEval is a benchmarking that offers challenges in multimedia retrieval, access and exploration to allow researchers working in computer science and other multimedia related field an opportunity to work on tasks that are related to human and social aspects of multimedia. MediaEval aims is to promote reproducible research that makes multimedia a positive force for society.
Emotion and theme recognition is a popular task in music information retrieval that is relevant for music search and recommendation systems. The goal of the task is to automatically recognize the emotions and themes conveyed in a music recording using machine learning algorithms. See more here
The team of the Institute of Computational Perception, namely Khaled Koutini, Shreyan Chowdhury, Verena Haunschmid, Hamid Eghbal-zadeh, Gerhard Widmer, won the challenge by developing the highest performing models to detect emotion and themes in music. The report detailing the work can be found here
Sep, 2019: Best Reviewer Awards: CP researchers Christine Bauer and Markus Schedl receive two Best Reviewer Awards at ACM Recommender Systems Conference (out of more than 200 reviewers). A third Best Reviewer Award goes to former CP member Peter Knees.
Sep, 2019: CP as strong contributor to this year's Ars Electronica Festival: CP is a strong contributor to this year's *Ars Electronica Festival*, and the newly established *AI x Music* focus in particular.
"Computers that Learn to Listen" - curated by Gerhard Widmer: a video that demonstrates some results of our research in the field of AI and Music, from autonomous drum robots to an automatic expressive accompaniment system.
"Recommenders and Intelligent Tools in Music Creation: Why, Why Not, and How?" - a workshop by Christine Bauer, Peter Knees, Richard Vogl, and Hansi Raber - will highlight the role of AI, Machine Learning-supported composition, and Recommender Systems in the process of music creation.
"Music Information Retrieval: Inside and Outside the Music" - a talk by Christine Bauer and Peter Knees: In scope of the AIxMusic Matinée, Christine Bauer and Peter Knees give a talk where they will highlight the use of intelligent audio analysis and social media mining for selected applications on music information retrieval and speculate on future directions.
Jul, 2019: Top Ranks for CP Teams in the DCASE 2019 Challenge: CP Teams achieve top ranks in the DCASE 2019 Challenge Task 1 and 2!
CP Results in the DCASE 2019 Acoustic Event Detection and Classification Challenge:
Task 1a - Acoustic Scene Classification.
Rank 2 (Team Ranking) for CP Team Khaled Koutini, Hamid Eghbal-zadeh & Gerhard Widmer (see Report)
Task 1b - Acoustic Scene Classification under Distribution Mismatch:
Rank 3 for CP Team Hamid Eghbal-zadeh, Khaled Koutini, and Gerhard Widmer (Report)
Rank 4 by CP Student! Team Paul Primus and David Eitelsebner (Report)
Task 1c - Open-Set Acoustic Scene Classification:
Rank 4 for SAL/CP Team Bernhard Lehner and Khaled Koutini (Report)
Task 2 - Audio Tagging with Noisy Labels and Minimal Supervision.
Rank 5 for CP Team Khaled Koutini, Hamid Eghbal-zadeh & Gerhard Widmer. (Report)
Jun, 2019: Study about Global and Country-specific Mainstreaminess Published: How mainstream are the listeners in my country and can we use this to improve music recommender systems? A recent study quantifies this "mainstreaminess" and presents music recommender systems which take this measure into account.
The researchers Christine Bauer and Markus Schedl published a study about global and country-specific mainstreaminess. In this, they analyze music preferences of 47 countries with respect to what is considered mainstream in a particular country. Furthermore, based on these findings, they evaluate recommendation approaches considering users’ mainstreaminess.
After publication, some of the main findings were summarized in these Austrian media articles (in German):
For detailed information, please find the full article here.
June, 2019: Con Espressione! Exhibit: The Con Espressione! Exhibit is an interactive system designed for popular science exhibitions. It demonstrates and enables joint human-computer control of expressive performance: the visitor controls overall tempo and loudness of classical piano pieces (such as Beethoven's "Moonlight" sonata Op.27 No.2) via hand movements (tracked by a LeapMotion sensor). In the background, our "Basis Mixer" expressive performance model adds subtle modifications to the performance, such as articulation and micro-timing (e.g., slight temporal differences in the note onsets when playing chords). The contribution of the Basis Mixer can be controlled and experimented with via a slider.
The exhibit was first shown at the la.la.lab Science Exhibition ("The Mathematics of Music") in Heidelberg, Germany (May - Dec. 2019). The source code is openly available via a github repository.
Okt, 2018: Best Paper and Best Poster Presentation Award: Best paper award at the 19th International Society for Music Information Retrieval Conference.
The paper "Learning to Listen, Read, and Follow: Score Following as a Reinforcement Learning Game (PDF)" by Matthias Dorfer, Florian Henkel, and Gerhard Widmer received the Best Paper Award and the Best Poster Presentation Award at the 19th International Society for Music Information Retrieval Conference.
Sep, 2018: Best Paper Award: Best paper award at the 21st International Conference on Digital Audio Effects. The paper "Towards Multi-Instrument Drum Transcription" by Richard Vogl (cp.jku PhD Student), Gerhard Widmer, and Peter Knees (TU Wien) received the 2nd Best Paper Award at the 21st International Conference on Digital Audio Effects.
Sep, 2018: BE OPEN - Science & Society Festival: Gerhard Widmer to curate a science pavilion on "AI & Music" at the BE OPEN Science & Society Festival,
Vienna, Sept. 8-12, 2018 (on the occasion of the 50th anniversary of the Austrian Science Fund (FWF).
Sep, 2018: BE OPEN - Science & Society Festival, Article on our AI & Music Pavillion at the FWF BE OPEN Science & Society Festival produced by Austran Newspaper "Die Presse".
May, 2018: ERC = Science2: On-line article in ERC = Science2 ("Mind-blowing science, from the European Research Council") on our work on computational models of expressive music performance in the Con Espressione Project.
Mar, 2018: STANDARD Article: Article in DER STANDARD on the FWF project "Fine-grained culture-aware music recommender systems" led by cp.jku researcher Christine Bauer.
- Feb, 2018: Noisey Interview: cp.jku researcher Christine Bauer was interviewed on music and artificial intelligence by Noisey Austria, an online youth magazine: Roboter statt Popstars: Was bedeutet künstliche Intelligenz für die Musikwelt? (in German).
- Feb, 2018: Workshop: cp.jku researcher Christine Bauer co-organizes the 1st Workshop on Multi-Method Evaluation of Personalized Systems at the 26th ACM Conference on User Modelling, Adaptation and Personalization (UMAP) 2018.
- Dec, 2017: Prize: cp.jku graduate Thomas Krismayer is awarded the Annual Prize of the Austrian Society for Artificial Intelligence (ÖGAI) 2017 for his Master thesis on "Prediction of User Traits from Music Listening Habits (see also his paper in the 2017 ACM CBMI Workshop)
- Dec, 2017: Best Paper Award: cp.jku researchers Markus Schedl and Christine Bauer receive the Best Paper Award for their paper "Introducing Global and Regional Mainstreaminess for Improving Personalized Music Recommendation" at the 15th International Conference on Advances in Mobile Computing & Multimedia (MoMM 2017).
- Nov, 2017: New open funded Ph.D. positions (at CP.JKU and other institutions) in the EU Marie Sklodowska-Curie Innovative Training Network (MSCA-ITN-ETN) New Frontiers in Music Information Processing. For a list of PhD projects and industry/cultural partners involved, and who to contact, see http://mip-frontiers.eecs.qmul.ac.uk.
- Nov, 2017: Markus Schedl to co-organize a workshop on "Intelligent Music Interfaces for Listening and Creation" at the ACM Intelligent User Interfaces 2018 conference.
- Oct, 2017: Demonstration of first prototype of our expressive accompaniment system The Accompanion v0.1 at the Late Breaking / Demo Papers Session at the ISMIR 2017 Conference, Suzhou, China.
Demo Videos on a Bösendorfer CEUS: Mozart Sonata K.545, 2nd mvt. (Werner Goebl); "The Wild Geese" (Gerhard Widmer)
- Oct, 2017: CP.JKU guest researcher Jan Hajic jr. (visiting from ÚFAL, Charles University Prague) and his team win the Internet of Emotions Hack Challenge at the Waves Vienna Music Hackday 2017 with Project "Trumpet" - a hack for reading back tweets with an appropriately (melo)dramatic voice and background music.
- Aug, 2017: CP.JKU Team (Khaled Koutini, Alina Imenina, Matthias Dorfer, Alexander Gruber, Markus Schedl) achieves the top results in the 2017 AcousticBrainz Genre Task at the MediaEval Benchmarking Initiative for Multimedia Evaluation.
Here is is a report on how we did it.
- Aug, 2017: New research opportunities for Ph.D. students and PostDocs:
A number of open research positions in at our department, in the context of the Con Espressione Project!
- Aug, 2017: Highly Commended Award in the 2017 Emerald Literati Network Awards for Excellence for Andreas Mladenow, Christine Bauer and Christine Strauss for their paper "Crowd logistics" in the International Journal of Web Information Systems.
- May, 2017: New project and opportunity for international PhD students at CP: Marie Sklodowska-Curie Action - Innovative Training Network (MSCA-ITN-ETN) New Frontiers in Music Information Processing (MIP-Frontiers) (4 years; 2017 - 2021) will be funded by the European Commission! Project to start in September 2017.
- April, 2017: New inter-disciplinary project on Computer-assisted Analysis of Herbert von Karajan's Musical Conducting Style (3 years; 2017 - 2020) will be funded by the Austrian Science Fund (FWF); project will start in June 2017.
- 2017-04-13: Gerhard Widmer to talk at the Karajan Music Tech Conference as part of the 50th Easter Festival (Osterfestspiele), Salzburg.
- Mar 9, 2017: Our drum robot won the second place in the IEEE Signal Processing Cup among 21 competitors. Besides tracking beats, it can also detect the beginning of a bar (downbeat) and the guitar pattern that is played by a musician in real-time. The whole system runs on a Raspberry Pi 3.
- Jan 13, 2017: Our BasisMixer computational model of expressive music performance is said to have passed a musical "Turing Test" (producing a piano performance whose "humanness" as judged by listeners is undistinguishable from a human musician's [and ranking best, in this respect, among a number of algorithms]) in a recent study ("Algorithms Can Mimic Human Piano Performance") by E. Schubert et al., published in J.New.Mus.Res. (Jan. 2017)
- Dec 27, 2016: FWF project "Social Media Mining for Multimodal Music Retrieval" led by Markus Schedl in the media
- Jul 27, 2016: CP Team (Hamid Eghbal-Zadeh, Bernhard Lehner, Matthias Dorfer) achieves Ranks 1 and 2 (among 49 competing entries) in the Audio Scene Classification Task at the DCASE 2016 Acoustic Event Detection and Classification Challenge. Here is a report on how we did it.
- Jun 23, 2016: Gerhard Widmer named "Vorarlberger des Jahres z'Wian 2016"
- Apr 16, 2016: Article in Wiener Zeitung - Future on Gerhard Widmer's ERC-funded Con Espressione project: "Wie musikalisch ein Computer sein kann"
- Dec 22, 2015: cp.jku graduate Stefan Neumüller wins the Adolf-Adam-Award 2015 for distinguished master's theses in computer science for his thesis "Active Appearance Models for Face Recognition"
- Nov 25, 2015: Portrait of Gerhard Widmer in Science Magazine Heureka: "Musikwahrnehmung im Computer"
- Nov 02, 2015: Best Paper Award for Andreas Arzt and Gerhard Widmer at the 16th International Society for Music Information Retrieval conference (ISMIR 2015) for their paper Real-Time Music Tracking Using Multiple Performances as a Reference
- Oct 15, 2015: Article in Die Presse on the ERC-funded Con Espressione project: "Musik verstehen mit dem Computer"
- Oct 12, 2015: Gerhard Widmer to give a public ARTEMATICA 2015 Wolfgang Pauli Lecture on the Con Espressione project, at the Künstlerhaus Vienna
- Aug 13, 2015: Video of Gerhard Widmer controlling a performance on the Bösendorfer CEUS computer-monitored piano via a Midi Theremin (with interview; produced by Austrian Science Fund FWF)
- Aug 13, 2015: Portrait of Gerhard Widmer in SciLog (E-Magazine of the Austrian Science Fund FWF): "Abseits vom Mainstream" (German); "Beyond the Mainstream" (English).
- Jul 01, 2015: Interview mit Gerhard Widmer in Der Standard: "Musik braucht eine bestimmte Menge Redundanz" (online: "Musik braucht Wiederholungen")
- Jun 19, 2015: Richard Vogl wins the prizes for Best Bitalino Hack and Best Juce Hack at the Music Hack Day 2015 in Barcelona (watch the presentation of his hack)
- Jun 02, 2015: Call for Papers: ACM TIST Special Issue on Intelligent Music Systems and Applications
- May 04, 2015: Gerhard Widmer receives an ERC Advanced Grant from the European Research Council (ERC): € 2.3 million for the project Con Espressione
- May 03, 2015: Call for Papers for the 2nd International Workshop on Social Media Retrieval and Analysis in conjunction with IEEE ICDM 2015, Atlantic City, NJ, USA
- Feb 14, 2015: Two articles in Die Presse on cp.jku research: "Eine Sinfonie mit gewissen Extras" und "Der digitale DJ empfiehlt die beste Melodie" (print article)
- Feb 07, 2015: World premiere in the Concertgebouw Amsterdam: Our live music tracking system successfully followed a live performance of Richard Strauss' Alpensinfonie by the Royal Concertgebouw Orchestra. Here's an article on this in Die Presse and a radio interview on Ö1.
- Feb 05, 2015: Radio interview with Gerhard Widmer on the upcoming Concertgebouw concert in Ö1 Kulturjournal (MP3) and Ö1 Mittagsjournal (MP3)
- Dec 17, 2014: Gerhard Widmer on the PHENICX project and the upcoming AI-augmented concert by the Royal Concertgebouw Orchestra, Amsterdam in Der Standard and Wiener Zeitung
- Oct 01, 2014: Call for Papers: UMUAI - Special Issue on Physiology in Personalized Systems
- Sep 06, 2014: Best Student Paper Award for the paper "Quad-Based Audio Fingerprinting Robust to Time and Frequency Scaling" by Reinhard Sonnleitner and Gerhard Widmer at the 17th International Conference on Digital Audio Effects (DAFx 2014), Erlangen, Germany
- Sep 01, 2014: Best PAIS Demo Award for the "The Piano Music Companion" by A. Arzt, S. Böck, S. Flossmann, H. Frostel, M. Gasser, C.C.S. Liem, and G. Widmer at the 8th International Conference on the Prestigious Applications of Intelligent Systems (PAIS 2014) in conjunction with the 21st European Conference on Artificial Intelligence (ECAI 2014), Prague, Czech Republic
- May 13, 2014: Artikel auf nachrichten.at: "Königliches Orchester spielt mit Computerprogramm der Kepler-Uni"
- May 06, 2014: cp.jku researcher Andreas Arzt named Oberösterreicher des Tages
- Mar 26, 2014: CP & OFAI Score-Performance Alignment Technology integrated into Issue # 5 (on Beethoven's 3rd Symphony) of the e-magazine RCO Editions (iPad-based e-magazine by the world-famous Royal Concertgebouw Orchestra Amsterdam)!
- Mar 13, 2014: Call for Papers: UMUAI - Special Issue on Personality in Personalized Systems
- Jan 29, 2014: Best Paper Award and Best Demo Award at the AES 53rd International Conference on Semantic Audio, London, UK
- Oct 16, 2013: Artikel über Markus Schedl und Forschungsprojekt FWF P22856-N23 in Bild der Wissenschaft: "Immer den passenden Groove"
- May 05, 2013: Artikel über Gerhard Widmer in Die Presse am Sonntag: "Wie Computer hören lernen"
- Apr 03, 2013: Artikel in Der Standard über cp.jku Forschungsprojekt FWF P22856-N23: "Der Alltag bestimmt den Rhythmus"
>> siehe auch weitere Artikel in OÖ Nachrichten, krone.at, APA Science, Österreich Journal und Bezirksrundschau
- Mar 20, 2013: Artikel über Gerhard Widmer im Universum Magazin: "Herr der leisen Töne"
- Feb 13, 2013: Exciting new topics for student projects and Master's theses in the context of the PHENICX project
- Feb 01, 2013: New EU-FP7 project Performances as Highly Enriched aNd Interactive Concert eXperiences (PHENICX) started
- Oct 03, 2012: The cp.jku powered ISMIR 2012 Cloud Browser is online
- Aug 31, 2012: Das Institut für Computational Perception ist übersiedelt. Sie finden uns nun im Science Park 3, 4. Stock.
- May 14, 2012: cp.jku's former PhD student Dominik Schnitzer and his Wolperdinger large-scale music recommender are featured on Science ORF.at and Ö1 Wissen aktuell
- Apr 23, 2012: Gerhard Widmer and Peter Knees presented our arts project sound/tracks at the ERC Gala in the Aula der Wissenschaften in a live performance on a Bösendorfer CEUS Grand Piano
- Feb 19, 2012: New Section: Hall of Fame
- Feb 02, 2012: cp.jku's team "Die Polarkoordinatoren" wins the 6th annual Johannes Kepler University Ice Stock Sport Competition (also known as Bavarian Curling)
- Jan 12, 2012: cp.jku is co-organizing the 4th International Workshop on Advances in Music Information Research – AdMIRe 2012: "The Web of Music" in conjunction with the www conference in Lyon, France
- Jan 12, 2012: Our arts project sound/tracks has been exhibited at the Media Arts Festival in Miyazaki, Japan
- Nov 06, 2011: cp.jku researcher Klaus Seyerlehner receives the Award of Excellence 2011 for his excellent PhD thesis
- Mar 02, 2011: Artikel in den Univationen: "Musikähnlichkeit genau berechnet"
- Feb 19, 2011: Artikel in den OÖ Nachrichten: "Computer mit Musikgeschmack als Konkurrenz zu Guetta"
- Feb 08, 2011: Well-funded PhD scholarships from National University of Singapore (NUS) are available. In case of interest, please contact Markus Schedl.
- Dec 08, 2010: Our arts project sound/tracks has been selected as Jury Recommended Work at the 14th Japan Media Arts Festival